fastannotate: move some global state mutation to extsetup()

Differential Revision: https://phab.mercurial-scm.org/D4202

hgext/fastannotate/__init__.py

@@ -1,193 +1,193 b''
 # Copyright 2016-present Facebook. All Rights Reserved.
 #
 # fastannotate: faster annotate implementation using linelog
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """yet another annotate implementation that might be faster (EXPERIMENTAL)
 
 The fastannotate extension provides a 'fastannotate' command that makes
 use of the linelog data structure as a cache layer and is expected to
 be faster than the vanilla 'annotate' if the cache is present.
 
 In most cases, fastannotate requires a setup that mainbranch is some pointer
 that always moves forward, to be most efficient.
 
 Using fastannotate together with linkrevcache would speed up building the
 annotate cache greatly. Run "debugbuildlinkrevcache" before
 "debugbuildannotatecache".
 
 ::
 
     [fastannotate]
     # specify the main branch head. the internal linelog will only contain
     # the linear (ignoring p2) "mainbranch". since linelog cannot move
     # backwards without a rebuild, this should be something that always moves
     # forward, usually it is "master" or "@".
     mainbranch = master
 
     # fastannotate supports different modes to expose its feature.
     # a list of combination:
     # - fastannotate: expose the feature via the "fastannotate" command which
     #   deals with everything in a most efficient way, and provides extra
     #   features like --deleted etc.
     # - fctx: replace fctx.annotate implementation. note:
     #     a. it is less efficient than the "fastannotate" command
     #     b. it will make it practically impossible to access the old (disk
     #        side-effect free) annotate implementation
     #     c. it implies "hgweb".
     # - hgweb: replace hgweb's annotate implementation. conflict with "fctx".
     # (default: fastannotate)
     modes = fastannotate
 
     # default format when no format flags are used (default: number)
     defaultformat = changeset, user, date
 
     # serve the annotate cache via wire protocol (default: False)
     # tip: the .hg/fastannotate directory is portable - can be rsynced
     server = True
 
     # build annotate cache on demand for every client request (default: True)
     # disabling it could make server response faster, useful when there is a
     # cronjob building the cache.
     serverbuildondemand = True
 
     # update local annotate cache from remote on demand
     client = False
 
     # path to use when connecting to the remote server (default: default)
     remotepath = default
 
     # minimal length of the history of a file required to fetch linelog from
     # the server. (default: 10)
     clientfetchthreshold = 10
 
     # use flock instead of the file existence lock
     # flock may not work well on some network filesystems, but they avoid
     # creating and deleting files frequently, which is faster when updating
     # the annotate cache in batch. if you have issues with this option, set it
     # to False. (default: True if flock is supported, False otherwise)
     useflock = True
 
     # for "fctx" mode, always follow renames regardless of command line option.
     # this is a BC with the original command but will reduced the space needed
     # for annotate cache, and is useful for client-server setup since the
     # server will only provide annotate cache with default options (i.e. with
     # follow). do not affect "fastannotate" mode. (default: True)
     forcefollow = True
 
     # for "fctx" mode, always treat file as text files, to skip the "isbinary"
     # check. this is consistent with the "fastannotate" command and could help
     # to avoid a file fetch if remotefilelog is used. (default: True)
     forcetext = True
 
     # use unfiltered repo for better performance.
     unfilteredrepo = True
 
     # sacrifice correctness in some corner cases for performance. it does not
     # affect the correctness of the annotate cache being built. the option
     # is experimental and may disappear in the future (default: False)
     perfhack = True
 """
 
 # TODO from import:
 # * `branch` is probably the wrong term, throughout the code.
 #
 # * replace the fastannotate `modes` configuration with a collection
 #   of booleans.
 #
 # * Use the templater instead of bespoke formatting
 #
 # * rename the config knob for updating the local cache from a remote server
 #
-# * move various global-setup bits to extsetup() or reposetup()
-#
 # * move `flock` based locking to a common area
 #
 # * revise wireprotocol for sharing annotate files
 #
 # * figure out a sensible default for `mainbranch` (with the caveat
 #   that we probably also want to figure out a better term than
 #   `branch`, see above)
 #
 # * format changes to the revmap file (maybe use length-encoding
 #   instead of null-terminated file paths at least?)
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     error as hgerror,
     localrepo,
     registrar,
     util,
 )
 
 from . import (
     commands,
     context,
     protocol,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = commands.cmdtable
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('fastannotate', 'modes', default=['fastannotate'])
 configitem('fastannotate', 'server', default=False)
 configitem('fastannotate', 'useflock', default=True)
 configitem('fastannotate', 'client', default=False)
 configitem('fastannotate', 'unfilteredrepo', default=True)
 configitem('fastannotate', 'defaultformat', default=['number'])
 configitem('fastannotate', 'perfhack', default=False)
 configitem('fastannotate', 'mainbranch')
 configitem('fastannotate', 'forcetext', default=True)
 configitem('fastannotate', 'forcefollow', default=True)
 configitem('fastannotate', 'clientfetchthreshold', default=10)
 configitem('fastannotate', 'serverbuildondemand', default=True)
 configitem('fastannotate', 'remotepath', default='default')
 
 def _flockavailable():
     try:
         import fcntl
         fcntl.flock
     except StandardError:
         return False
     else:
         return True
 
 def uisetup(ui):
     modes = set(ui.configlist('fastannotate', 'modes'))
     if 'fctx' in modes:
         modes.discard('hgweb')
     for name in modes:
         if name == 'fastannotate':
             commands.registercommand()
         elif name == 'hgweb':
             from . import support
             support.replacehgwebannotate()
         elif name == 'fctx':
             from . import support
             support.replacefctxannotate()
             commands.wrapdefault()
         else:
             raise hgerror.Abort(_('fastannotate: invalid mode: %s') % name)
 
     if ui.configbool('fastannotate', 'server'):
         protocol.serveruisetup(ui)
 
     if ui.configbool('fastannotate', 'useflock', _flockavailable()):
         context.pathhelper.lock = context.pathhelper._lockflock
 
+def extsetup(ui):
     # fastannotate has its own locking, without depending on repo lock
+    # TODO: avoid mutating this unless the specific repo has it enabled
     localrepo.localrepository._wlockfreeprefix.add('fastannotate/')
 
 def reposetup(ui, repo):
     if ui.configbool('fastannotate', 'client'):
         protocol.clientreposetup(ui, repo)

hgext/fastannotate/protocol.py

@@ -1,227 +1,229 b''
 # Copyright 2016-present Facebook. All Rights Reserved.
 #
 # protocol: logic for a server providing fastannotate support
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import contextlib
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     extensions,
     hg,
     localrepo,
     scmutil,
     wireprotov1peer,
     wireprotov1server,
 )
 from . import context
 
 # common
 
 def _getmaster(ui):
     """get the mainbranch, and enforce it is set"""
     master = ui.config('fastannotate', 'mainbranch')
     if not master:
         raise error.Abort(_('fastannotate.mainbranch is required '
                             'for both the client and the server'))
     return master
 
 # server-side
 
 def _capabilities(orig, repo, proto):
     result = orig(repo, proto)
     result.append('getannotate')
     return result
 
 def _getannotate(repo, proto, path, lastnode):
     # output:
     #   FILE := vfspath + '\0' + str(size) + '\0' + content
     #   OUTPUT := '' | FILE + OUTPUT
     result = ''
     buildondemand = repo.ui.configbool('fastannotate', 'serverbuildondemand',
                                        True)
     with context.annotatecontext(repo, path) as actx:
         if buildondemand:
             # update before responding to the client
             master = _getmaster(repo.ui)
             try:
                 if not actx.isuptodate(master):
                     actx.annotate(master, master)
             except Exception:
                 # non-fast-forward move or corrupted. rebuild automically.
                 actx.rebuild()
                 try:
                     actx.annotate(master, master)
                 except Exception:
                     actx.rebuild() # delete files
             finally:
                 # although the "with" context will also do a close/flush, we
                 # need to do it early so we can send the correct respond to
                 # client.
                 actx.close()
         # send back the full content of revmap and linelog, in the future we
         # may want to do some rsync-like fancy updating.
         # the lastnode check is not necessary if the client and the server
         # agree where the main branch is.
         if actx.lastnode != lastnode:
             for p in [actx.revmappath, actx.linelogpath]:
                 if not os.path.exists(p):
                     continue
                 content = ''
                 with open(p, 'rb') as f:
                     content = f.read()
                 vfsbaselen = len(repo.vfs.base + '/')
                 relpath = p[vfsbaselen:]
                 result += '%s\0%s\0%s' % (relpath, len(content), content)
     return result
 
 def _registerwireprotocommand():
     if 'getannotate' in wireprotov1server.commands:
         return
     wireprotov1server.wireprotocommand(
         'getannotate', 'path lastnode')(_getannotate)
 
 def serveruisetup(ui):
     _registerwireprotocommand()
     extensions.wrapfunction(wireprotov1server, '_capabilities', _capabilities)
 
 # client-side
 
 def _parseresponse(payload):
     result = {}
     i = 0
     l = len(payload) - 1
     state = 0 # 0: vfspath, 1: size
     vfspath = size = ''
     while i < l:
         ch = payload[i]
         if ch == '\0':
             if state == 1:
                 result[vfspath] = buffer(payload, i + 1, int(size))
                 i += int(size)
                 state = 0
                 vfspath = size = ''
             elif state == 0:
                 state = 1
         else:
             if state == 1:
                 size += ch
             elif state == 0:
                 vfspath += ch
         i += 1
     return result
 
 def peersetup(ui, peer):
     class fastannotatepeer(peer.__class__):
         @wireprotov1peer.batchable
         def getannotate(self, path, lastnode=None):
             if not self.capable('getannotate'):
                 ui.warn(_('remote peer cannot provide annotate cache\n'))
                 yield None, None
             else:
                 args = {'path': path, 'lastnode': lastnode or ''}
                 f = wireprotov1peer.future()
                 yield args, f
                 yield _parseresponse(f.value)
     peer.__class__ = fastannotatepeer
 
 @contextlib.contextmanager
 def annotatepeer(repo):
     ui = repo.ui
 
     remotepath = ui.expandpath(
         ui.config('fastannotate', 'remotepath', 'default'))
     peer = hg.peer(ui, {}, remotepath)
 
     try:
         yield peer
     finally:
         peer.close()
 
 def clientfetch(repo, paths, lastnodemap=None, peer=None):
     """download annotate cache from the server for paths"""
     if not paths:
         return
 
     if peer is None:
         with annotatepeer(repo) as peer:
             return clientfetch(repo, paths, lastnodemap, peer)
 
     if lastnodemap is None:
         lastnodemap = {}
 
     ui = repo.ui
     results = []
     with peer.commandexecutor() as batcher:
         ui.debug('fastannotate: requesting %d files\n' % len(paths))
         for p in paths:
             results.append(batcher.callcommand(
                 'getannotate',
                 {'path': p, 'lastnode':lastnodemap.get(p)}))
 
     ui.debug('fastannotate: server returned\n')
     for result in results:
         r = result.result()
         for path in sorted(r):
             # ignore malicious paths
             if not path.startswith('fastannotate/') or '/../' in (path + '/'):
                 ui.debug('fastannotate: ignored malicious path %s\n' % path)
                 continue
             content = r[path]
             if ui.debugflag:
                 ui.debug('fastannotate: writing %d bytes to %s\n'
                          % (len(content), path))
             repo.vfs.makedirs(os.path.dirname(path))
             with repo.vfs(path, 'wb') as f:
                 f.write(content)
 
 def _filterfetchpaths(repo, paths):
     """return a subset of paths whose history is long and need to fetch linelog
     from the server. works with remotefilelog and non-remotefilelog repos.
     """
     threshold = repo.ui.configint('fastannotate', 'clientfetchthreshold', 10)
     if threshold <= 0:
         return paths
 
     master = repo.ui.config('fastannotate', 'mainbranch') or 'default'
 
     result = []
     for path in paths:
         try:
             if len(repo.file(path)) >= threshold:
                 result.append(path)
         except Exception: # file not found etc.
             result.append(path)
 
     return result
 
 def localreposetup(ui, repo):
     class fastannotaterepo(repo.__class__):
         def prefetchfastannotate(self, paths, peer=None):
             master = _getmaster(self.ui)
             needupdatepaths = []
             lastnodemap = {}
             try:
                 for path in _filterfetchpaths(self, paths):
                     with context.annotatecontext(self, path) as actx:
                         if not actx.isuptodate(master, strict=False):
                             needupdatepaths.append(path)
                             lastnodemap[path] = actx.lastnode
                 if needupdatepaths:
                     clientfetch(self, needupdatepaths, lastnodemap, peer)
             except Exception as ex:
                 # could be directory not writable or so, not fatal
                 self.ui.debug('fastannotate: prefetch failed: %r\n' % ex)
     repo.__class__ = fastannotaterepo
 
 def clientreposetup(ui, repo):
     _registerwireprotocommand()
     if isinstance(repo, localrepo.localrepository):
         localreposetup(ui, repo)
+    # TODO: this mutates global state, but only if at least one repo
+    # has the extension enabled. This is probably bad for hgweb.
     if peersetup not in hg.wirepeersetupfuncs:
         hg.wirepeersetupfuncs.append(peersetup)